Hacker News2h agoenergy 109
Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)
image: Hacker News
A configuration mismatch in GLM 5.3 on Workers AI triggered an SGLang bug that exposed KV cache pages across requests. Here is how we addressed the issue.
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.